CN102519973A - Method for detecting lip defect of PET bottle or bottle parison - Google Patents

Method for detecting lip defect of PET bottle or bottle parison Download PDF

Info

Publication number
CN102519973A
CN102519973A CN2011104130759A CN201110413075A CN102519973A CN 102519973 A CN102519973 A CN 102519973A CN 2011104130759 A CN2011104130759 A CN 2011104130759A CN 201110413075 A CN201110413075 A CN 201110413075A CN 102519973 A CN102519973 A CN 102519973A
Authority
CN
China
Prior art keywords
bottle
image
pet
pet bottle
lip
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2011104130759A
Other languages
Chinese (zh)
Other versions
CN102519973B (en
Inventor
王贵锦
张树君
施陈博
国磊
姜辉
何贝
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Mingjia Package Inspection Technology Co Ltd
Original Assignee
Shandong Mingjia Package Inspection Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Mingjia Package Inspection Technology Co Ltd filed Critical Shandong Mingjia Package Inspection Technology Co Ltd
Priority to CN201110413075.9A priority Critical patent/CN102519973B/en
Publication of CN102519973A publication Critical patent/CN102519973A/en
Application granted granted Critical
Publication of CN102519973B publication Critical patent/CN102519973B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a method for detecting the lip defect of a PET bottle or a bottle parison. According to the invention, a lip annular zone image is acquired; the image is transversally expanded at a tangential point; gradients are calculated on a transversal direction; a radial sum of the transversal gradients are adopted as characteristic parameters, such that the lip defect of the PET bottle or the bottle parison can be determined and analyzed. The method is simple, and can be used for detecting problems such as bottle lip knocking, bottle lip damages and cracks. With the method, detection precision is improved, and error rejection rate can be greatly reduced.

Description

A kind of method that detects PET bottle or bottle embryo bottle mouth defect
Technical field
The invention belongs to the mechanical vision inspection technology field, especially relate to the method for a kind of PET of detection bottle or bottle embryo bottle mouth defect.
Background technology
At present, the manufacturing process of PET bottle all is to carry out embryo earlier, through bottle blowing machine it is shaped then, need check in process of production whether the upper surface of bottleneck exists breakage, prevents after capping, to leak gas, and produces unacceptable product.The detection method of this respect seldom; Because rotational line speed is very fast; And the folder bottle system is not steady especially, and the lightness of taking is also inhomogeneous, and general method is difficult to stable detection and goes out different defects; Also be prone to Lou rejecting and mistake and reject phenomenon, press for the detection that a kind of good detection method is accomplished this product.
Summary of the invention
The objective of the invention is: the method that a kind of method is easy, accuracy of detection is high detection PET bottle or bottle embryo bottle mouth defect are provided.
Technical scheme of the present invention is: the method that detects the bottle mouth defect of PET bottle or bottle embryo may further comprise the steps:
(1) gather PET bottle or bottle embryo bottleneck image, and the input computer system;
(2) extraction flask choma area image, with image from the point of contact horizontal spreading, ask gradient in a lateral direction;
(3) select the Sobel wave filter to image filtering, calculate transverse gradients;
(4) transverse gradients of trying to achieve is radially being sued for peace and assignment is given original matrix;
(5) according to transverse gradients radially with as characteristic quantity, discriminatory analysis goes out the bottle mouth defect of PET bottle or bottle embryo.
The invention has the beneficial effects as follows: this method has very succinctly effectively solved the problem of PET bottle or the detection of bottle embryo bottleneck; On high-speed automated production line; To pet container carry out before the bottle blowing or bottle blowing after bottleneck detect and handle; Can detect problems such as bottleneck is damaged, bottleneck breakage, crackle, when improving accuracy of detection, also greatly reduce mistake and reject.
Description of drawings
Fig. 1 is that synoptic diagram is used in detection of the present invention.
Embodiment
The method that the present invention detects PET bottle or bottle embryo bottle mouth defect may further comprise the steps:
Step (one): gather PET bottle or bottle embryo bottleneck image, and the input computer system.
Step (two): extraction flask choma area image, ask gradient in a lateral direction, horizontal direction is the tangential direction of corresponding original image, is about to bottle germ ring border circular areas image and seeks a point of contact, the horizontal spreading from the point of contact is asked gradient in a lateral direction.
Step (three): select the Sobel wave filter to image filtering, calculate transverse gradients.Wave filter in the use formula (1-1) that the calculating of transverse gradients can be similar to carries out filtering to the bottle germ ring zone after extracting and obtains.
Formula (1-1):
Figure 182241DEST_PATH_IMAGE001
During as ; Obtain the Prewitt wave filter, it is vertically carrying out a mean filter processing.During as
Figure 454139DEST_PATH_IMAGE003
; Obtained the Frei wave filter, its shortcoming is to need Floating-point Computation.During as
Figure 338919DEST_PATH_IMAGE004
; Obtained the Sobel wave filter, it is similar to the level and smooth processing of Gauss one of vertical execution.In above three wave filters because the Sobel wave filter has used best smoothing filter, can effectively suppress noise, so its result who returns is best, thus select the Sobel wave filter to bottle germ ring image filtering to calculate transverse gradients.
Step (four): the transverse gradients of trying to achieve is radially being sued for peace and assignment is given original matrix.In the transverse gradients of trying to achieve, the position that peak value occurs is and collapses the damage fault location, and various disturbing factors are seeming more at random in the radial direction, but rule is apparent in view on tangential direction.In order to eliminate the even The noise of the brightness disproportionation that causes owing to reasons such as illumination, radially the gradient of trying to achieve is being sued for peace and assignment is given original matrix.
Step (five): radially and as characteristic quantity detect bottle mouth defect according to transverse gradients.
Fig. 1 is that synoptic diagram is used in detection of the present invention; Be the Grad after radially suing for peace; As can be seen from the figure; In that to decrease the zone very obvious with the difference of normal region to collapsing after the gradient summation in the radial direction, collapse decrease regional gradient and absolute value about 4000, and the value of normal region is less than 1000.According to transverse gradients radially and as the characteristic quantity discriminatory analysis go out the bottle mouth defect of PET bottle or bottle embryo, accuracy of detection is high, false drop rate is low.

Claims (1)

1. a method that detects the bottle mouth defect of PET bottle or bottle embryo is characterized in that, may further comprise the steps:
(1) gather PET bottle or bottle embryo bottleneck image, and the input computer system;
(2) extraction flask choma area image, with image from the point of contact horizontal spreading, ask gradient in a lateral direction;
(3) select the Sobel wave filter to image filtering, calculate transverse gradients;
(4) transverse gradients of trying to achieve is radially being sued for peace and assignment is given original matrix;
(5) according to transverse gradients radially with as characteristic quantity, discriminatory analysis goes out the bottle mouth defect of PET bottle or bottle embryo.
CN201110413075.9A 2011-12-10 2011-12-10 Method for detecting lip defect of PET bottle or bottle parison Active CN102519973B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110413075.9A CN102519973B (en) 2011-12-10 2011-12-10 Method for detecting lip defect of PET bottle or bottle parison

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110413075.9A CN102519973B (en) 2011-12-10 2011-12-10 Method for detecting lip defect of PET bottle or bottle parison

Publications (2)

Publication Number Publication Date
CN102519973A true CN102519973A (en) 2012-06-27
CN102519973B CN102519973B (en) 2014-06-25

Family

ID=46290963

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110413075.9A Active CN102519973B (en) 2011-12-10 2011-12-10 Method for detecting lip defect of PET bottle or bottle parison

Country Status (1)

Country Link
CN (1) CN102519973B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103308523A (en) * 2013-05-28 2013-09-18 清华大学 Method for detecting multi-scale bottleneck defects, and device for achieving method
CN104502359A (en) * 2014-12-10 2015-04-08 天津普达软件技术有限公司 Method for accurately detecting bottle blank and bottle opening defects
CN104764746A (en) * 2014-01-06 2015-07-08 山东明佳包装检测科技有限公司 Method for omnibearing detection of defect of PET bottle cap antitheft ring
CN105954301A (en) * 2016-06-22 2016-09-21 广东省自动化研究所 Bottleneck quality detection method based on machine vision
CN106841229A (en) * 2016-12-20 2017-06-13 浙江工业大学 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision
CN106952258A (en) * 2017-03-23 2017-07-14 南京汇川图像视觉技术有限公司 A kind of bottle mouth defect detection method based on gradient orientation histogram

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0324447A (en) * 1989-06-21 1991-02-01 Shokuhin Sangyo Onrain Sensor Gijutsu Kenkyu Kumiai Bottle-mouth inspecting method
CN101105459A (en) * 2007-05-15 2008-01-16 广州市万世德包装机械有限公司 Empty bottle mouth defect inspection method and device
CN102162797A (en) * 2010-11-24 2011-08-24 哈尔滨工业大学(威海) Algorithm for detecting glass bottle neck damage and bottle bottom dirt

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0324447A (en) * 1989-06-21 1991-02-01 Shokuhin Sangyo Onrain Sensor Gijutsu Kenkyu Kumiai Bottle-mouth inspecting method
CN101105459A (en) * 2007-05-15 2008-01-16 广州市万世德包装机械有限公司 Empty bottle mouth defect inspection method and device
CN102162797A (en) * 2010-11-24 2011-08-24 哈尔滨工业大学(威海) Algorithm for detecting glass bottle neck damage and bottle bottom dirt

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
罗琳 等: "可乐瓶口缺陷快速检测系统的研制", 《计算机测量与控制》, vol. 16, no. 4, 31 December 2008 (2008-12-31) *
陶跃珍 等: "基于图像处理的啤酒瓶瓶口缺陷检测", 《装备制造技术》, no. 5, 31 December 2009 (2009-12-31) *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103308523A (en) * 2013-05-28 2013-09-18 清华大学 Method for detecting multi-scale bottleneck defects, and device for achieving method
CN104764746A (en) * 2014-01-06 2015-07-08 山东明佳包装检测科技有限公司 Method for omnibearing detection of defect of PET bottle cap antitheft ring
CN104764746B (en) * 2014-01-06 2017-04-05 山东明佳包装检测科技有限公司 A kind of detection method of comprehensive PET bottle lid anti-theft ring defect
CN104502359A (en) * 2014-12-10 2015-04-08 天津普达软件技术有限公司 Method for accurately detecting bottle blank and bottle opening defects
CN105954301A (en) * 2016-06-22 2016-09-21 广东省自动化研究所 Bottleneck quality detection method based on machine vision
CN105954301B (en) * 2016-06-22 2019-08-06 广东省智能制造研究所 A kind of bottleneck quality detection method based on machine vision
CN106841229A (en) * 2016-12-20 2017-06-13 浙江工业大学 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision
CN106952258A (en) * 2017-03-23 2017-07-14 南京汇川图像视觉技术有限公司 A kind of bottle mouth defect detection method based on gradient orientation histogram
CN106952258B (en) * 2017-03-23 2019-12-03 南京汇川图像视觉技术有限公司 A kind of bottle mouth defect detection method based on gradient orientation histogram

Also Published As

Publication number Publication date
CN102519973B (en) 2014-06-25

Similar Documents

Publication Publication Date Title
WO2022027949A1 (en) Machine vision-based detecting method and system for glass bottle bottom defects
CN102519973B (en) Method for detecting lip defect of PET bottle or bottle parison
CN105334219B (en) A kind of bottle mouth defect detection method of residual analysis dynamic threshold segmentation
CN109060836B (en) Machine vision-based high-pressure oil pipe joint external thread detection method
KR102201911B1 (en) Automated inline inspection and metrology using shadow-gram images
CN105954301B (en) A kind of bottleneck quality detection method based on machine vision
US9230318B2 (en) Analysis of the digital image of the external surface of a tyre and processing of false measurement points
CN104764746B (en) A kind of detection method of comprehensive PET bottle lid anti-theft ring defect
CN102496161A (en) Method for extracting contour of image of printed circuit board (PCB)
CN111862055B (en) Bubble turning cavity defect detection method based on image processing
CN107945155A (en) A kind of dentifrice tube shoulder defect inspection method based on Gabor filter
CN107490583A (en) A kind of intermediate plate defect inspection method based on machine vision
CN103759644A (en) Separating and refining type intelligent optical filter surface defect detecting method
CN106780437B (en) A kind of quick QFN chip plastic packaging image obtains and amplification method
CN103345743A (en) Image segmentation method for intelligent flaw detection of cell tail end
Yang et al. Vial bottle mouth defect detection based on machine vision
CN111161263A (en) Package flatness detection method and system, electronic equipment and storage medium
CN103163156A (en) Automatic grading method of lens defects based on machine vision technology
CN111815575A (en) Bearing steel ball part detection method based on machine vision
CN111307820A (en) Method for detecting surface defects of ceramic valve core based on machine vision
CN103278509A (en) Foam-appearance-based on-line beer detection method
CN101696876B (en) Visual detection method for VCM magnetic steel
CN105328533A (en) Edge grinding machine of glass
CN202533382U (en) Visual appearance on-line detection machine
Xu et al. Research on real-time quality inspection of PET bottle caps

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant